disaggregated inference thoughts

[mangoquill]

I don't think that's the whole story. I wouldn't optimize around that first. On my side the bigger swing came from the runtime and not the model. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.

[prompttinker44]

What exact setup are you running? What model, what runtime, and roughly what context size?

[sparrowshed]

Ran a quick check on my box. I couldn't reproduce the slowdown until I pushed context much higher.

[papermixer4]

Appreciate the detail. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimi

My first guess would be this: Before rebuilding anything, I'd test one clean baseline with Mixtral and compare from there.

[kernelrunner]

Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.

[rocmpath]

Ran a quick check on my box. On mini PC with MLX, I saw basically the same behavior. I expected the model choice to matter more than it did.